Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3634 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2147. Min Range: -1.2147

Max Act: 1.2147. Min Act: -0.0000

Data Index: 693641 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 1.2147. Min Range: -1.2147

Max Act: 1.0547. Min Act: -0.0000

Data Index: 403144 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 1.2147. Min Range: -1.2147

Max Act: 1.0031. Min Act: -0.0000

Data Index: 1048354 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.9755. Min Act: -0.0000

Data Index: 531012 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.8790. Min Act: -0.0000

Data Index: 27910 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.8107. Min Act: -0.0000

Data Index: 580178 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.8974. Min Act: -0.0000

Data Index: 787670 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.9615. Min Act: -0.0000

Data Index: 982487 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.8632. Min Act: -0.0000

Data Index: 112874 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.9531. Min Act: -0.0000

Data Index: 150566 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1097521 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.8501. Min Act: -0.0000

Data Index: 717704 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.7409. Min Act: -0.0000

Data Index: 475178 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.8501. Min Act: -0.0000

Data Index: 1252608 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1206515 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.8324. Min Act: -0.0000

Data Index: 382044 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.8040. Min Act: -0.0000

Data Index: 208945 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1112144 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.7856. Min Act: -0.0000

Data Index: 311463 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 1.2147. Min Range: -1.2147

Max Act: 0.8067. Min Act: -0.0000

Data Index: 184093 (C4 (Web Text))

Max Activating Token Index: 388